Korean Pro Go Player's Opening Recognition Using PCA
Although the history of the game of Go is more than 2,500 years, the theoretical studies of Go are still insufficient. In recent years a lot of studies using Artificial Intelligent (AI) have been conducted, but they do not provide the prominent theoretical reality. We applied traditional Principal Component Analysis (PCA) algorithm to the Go openings, which are the early stage in Go, to analyze them especially focused on the Go game records of the Korean top 10 professional Go players. We firstly analyzed the number of most significant eigenvectors capturing most of variance. Experimental result shows that among the 361 eigenvectors the eight most significant eigenvectors capture most of the variance (96.2%). We secondly used PCA classifier with Euclidean distance to recognize a pro player's opening to a class obtained from the training openings. Result shows that the best average recognition rate of 22% is so much lower than the recognition rates reported in face recognition research.